Borrowing it
Nothing to install: this file belongs to nawodyaishan/universal-mcp-sync. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nawodyaishan/universal-mcp-sync/main/.claude/skills/ux-bug-hunt/SKILL.mdgit clone --depth 1 https://github.com/nawodyaishan/universal-mcp-syncWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/ux-bug-hunt)<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/ux-bug-hunt"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/ux-bug-hunt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nawodyaishan/universal-mcp-sync/ux-bug-hunt"><img src="https://agentmods.dev/badge/skills/nawodyaishan/universal-mcp-sync/ux-bug-hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.02276 |
| Opus 5 | $0.00060 | $0.01138 |
| Sonnet 5 | $0.00024 | $0.00455 |
| Haiku 4.5 | $0.00012 | $0.00228 |
Grade A, and why
ux-bug-hunt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Bug-Hunt Iteration (usync / mcp-config-tui)
Scope: This skill is personalized to the
mcp-config-tuirepository. Every file path below is relative to the repo root (/Users/nawodyaishan/Documents/GitHub/mcp-config-tui). It will not work in any other project — the harness, scenarios, and IDs are project-owned.
The Docker-first UX harness (make ux-fake-prod) is a bug-funnel, not a
one-shot. Treat each iteration as a disciplined 4-stage loop and never skip
stage 3 (triage).
0. Required reading (read these before doing anything)
Specs & protocol (authoritative intent)
docs/specs/doctor-mode-phase12/ux-bug-hunt-protocol.md— the protocol; Docker run is the authoritative collection mechanismdocs/specs/doctor-mode-phase12/ux-flow-matrix.md— scenario matrix; every row is a contractdocs/specs/doctor-mode-phase12/spec.md— Phase 12 product intentdocs/specs/doctor-mode-phase12/plan.md— implementation plandocs/specs/doctor-mode-phase12/tasks.md— task breakdowndocs/specs/doctor-mode-phase12/user-flow-audit.md— audited journeys
Harness source (the runtime)
tests/ux-fake-prod/Dockerfile— fake-prod container buildtests/ux-fake-prod/docker-run.sh— entrypoint invoked bymake ux-fake-prodtests/ux-fake-prod/run-flow.sh— in-container scenario driver.dockerignore— keep this small; image hygiene affects determinism
Test runners (the matrix)
pkg/tui/dashboard_fake_prod_matrix_test.go— Docker matrix runnerpkg/tui/dashboard_flow_matrix_test.go— local shortcut matrix runnerpkg/tui/dashboard_flow_test.go— base teatest flows (read for patterns)pkg/tui/dashboard_golden_test.go— width/render goldens
TUI surface under test
pkg/tui/dashboard.go—DashboardModel, screens, key handlerspkg/tui/dashboard_view.go— allrender*functions and action barspkg/tui/dashboard_test.go— unit tests (regression baseline)
Artifacts (the output of every run)
artifacts/ux-fake-prod/— do not edit by hand; produced by Dockermatrix.json— canonical scenario × result tableissues.json— canonical open issues (DM-P<n>IDs)fake-prod-matrix.txt— human-readable matrixteatest-matrix.txt— local-test matrix- doctor JSON, plan JSON, fake home-after snapshot, TUI transcripts
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 159 lines · 119 tokens per session scan A bba181800d35
ux-bug-hunt is a skill published in the GitHub repository nawodyaishan/universal-mcp-sync (6 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 2,276 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…
tui-design
Design, build, refactor, or review terminal interfaces—full-screen TUIs, interactive prompts, and command-line tools. Use for terminal-app layout and UX, CLI behavior, ncurses-style tools, dashboards, REPLs, fzf-like pickers, and libraries such as Bubble Tea, Ratatui, Textual, or Ink, including requests that name a…
systematic-debugging
4-phase debugging protocol for diagnosing and fixing failing tests.
critique-theater
5-dimension critique panel; emits the critique.score signal that drives devloop convergence.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…